swiggy-address

Pass

Audited by Gen Agent Trust Hub on Sep 7, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill relies on the swiggy-cli tool to interact with the Swiggy service. It executes commands to list addresses, update profiles, and create or delete addresses.
  • [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to take user-provided strings (such as full addresses, names, or phone numbers) and insert them into shell command arguments. This presents a potential surface for command injection if the agent does not properly escape or sanitize the input before execution.
  • Ingestion points: User-supplied address, name, and phone fields processed in SKILL.md.
  • Boundary markers: None present.
  • Capability inventory: Shell command execution via swiggy-cli across all instructions.
  • Sanitization: No explicit sanitization or validation steps are defined in the instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 7, 2026, 10:16 AM
Security Audit — agent-trust-hub — swiggy-address